Electrocardiogram-based sleep analysis for sleep apnea screening and diagnosis

Association of self-reported and objective sleep disturbance with the spectrum of gastroesophageal reflux disease

STUDY OBJECTIVES

The relationship between obstructive sleep apnea (OSA) and gastroesophageal reflux disease (GERD) is complex. We aimed to determine the association of self-reported and objective sleep parameters with diverse manifestations of the GERD spectrum.

METHODS

We prospectively recruited 561 individuals who underwent an electrocardiogram-based cardiopulmonary coupling for OSA screening during a health check-up. All participants received the Reflux Disease Questionnaire and an upper endoscopy to determine the presence of troublesome reflux symptoms and erosive esophagitis (EE). Sleep quality was evaluated by the Pittsburgh Sleep Quality Index and sleep dysfunction was defined as a Pittsburgh Sleep Quality Index score > 5. OSA was defined as a cardiopulmonary coupling-derived apnea-hypopnea index exceeding 15 events/h. Comparisons were made between participants on the GERD spectrum with respect to their various self-reported and objective sleep parameters.

RESULTS

Among the 277 patients with GERD (49.4%), 198 (35.3%) had EE. Patients with GERD had higher PSQI scores (6.99 ± 3.97 vs 6.07 ± 3.73, P = .005) and a higher prevalence of sleep dysfunction (60.6% vs 49.6%, P = .009). Patients with EE had a higher prevalence of OSA (42.9% vs 33.9%, P = .034). Along the GERD spectrum, symptomatic patients with EE had the highest PSQI scores and prevalence of sleep dysfunction (70.7%), while asymptomatic patients with EE had the highest prevalence of OSA (44%).

CONCLUSIONS

Our findings indicate a high prevalence of sleep dysfunction among individuals with GERD. Furthermore, patients on the GERD spectrum are prone to experiencing a range of self-reported and objective sleep disturbances.

CITATION

Hu K-Y, Tseng P-H, Hsu W-C, et al. Association of self-reported and objective sleep disturbance with the spectrum of gastroesophageal reflux disease. J Clin Sleep Med. 2024;20(6):911-920.

Deep learning of sleep apnea-hypopnea events for accurate classification of obstructive sleep apnea and determination of clinical severity

BACKGROUND

/Objective: Automatic apnea/hypopnea events classification, crucial for clinical applications, often faces challenges, particularly in hypopnea detection. This study aimed to evaluate the efficiency of a combined approach using nasal respiration flow (RF), peripheral oxygen saturation (SpO2), and ECG signals during polysomnography (PSG) for improved sleep apnea/hypopnea detection and obstructive sleep apnea (OSA) severity screening.

METHODS

An Xception network was trained using main features from RF, SpO2, and ECG signals obtained during PSG. In addition, we incorporated demographic data for enhanced performance. The detection of apnea/hypopnea events was based on RF and SpO2 feature sets, while the screening and severity categorization of OSA utilized predicted apnea/hypopnea events in conjunction with demographic data.

RESULTS

Using RF and SpO2 feature sets, our model achieved an accuracy of 94 % in detecting apnea/hypopnea events. For OSA screening, an exceptional accuracy of 99 % and an AUC of 0.99 were achieved. OSA severity categorization yielded an accuracy of 93 % and an AUC of 0.91, with no misclassification between normal and mild OSA versus moderate and severe OSA. However, classification errors predominantly arose in cases with hypopnea-prevalent participants.

CONCLUSIONS

The proposed method offers a robust automatic detection system for apnea/hypopnea events, requiring fewer sensors than traditional PSG, and demonstrates exceptional performance. Additionally, the classification algorithms for OSA screening and severity categorization exhibit significant discriminatory capacity.

Improved Sleep Affects Epigastric Pain in Functional Dyspepsia by Reducing the Levels of Inflammatory Mediators

INTRODUCTION

The pathogenesis of epigastric pain in functional dyspepsia (FD) is complex. The study aims to explore the effect of sleep improvement on this symptom.

METHODS

In total, 120 patients with FD-associated epigastric pain and insomnia were randomly divided into experimental and control groups using the envelope method. After applying the exclusion criteria, 107 patients were enrolled in the experimental (56 patients) and control (51 patients) groups. Insomnia was graded according to the Pittsburgh Sleep Quality Index (PSQI). In the experimental group, eszopiclone 3 mg, eszopiclone 3 mg + estazolam 1 mg, and eszopiclone 3 mg + estazolam 2 mg were given to patients with mild, moderate, and severe insomnia, respectively. In the control group, patients were given 1, 2, or 3 tablets of vitamin B complex. Patient sleep quality was monitored with Sleepthing. Epigastric pain was evaluated with a Numeric Rating Scale. The serum levels of IL-1β, IL-6, IL-8, and tumor necrosis factor-α (TNF-α) were measured by enzyme-linked immunosorbent assay. Pain scores, sleep parameters, and serum levels of inflammatory mediators were compared before and after treatment.

RESULTS

After treatment, the pain scores, sleep parameters, and TNF-α and IL-6 levels in the experimental group were significantly lower than those in the control group (p < 0.05). PSQI insomnia scores were significantly associated with pain scores, IL-6, and TNF-α (p < 0.05) but not in IL-8 and IL-1β levels (p > 0.05) among the three groups.

CONCLUSIONS

Improving sleep with eszopiclone and/or estazolam alleviates FD-associated epigastric pain, possibly by inhibiting related downstream transmission pathways and reducing the release of inflammatory mediators.

Comparative study of the SleepImage ring device and polysomnography for diagnosing obstructive sleep apnea

Purpose We aim to evaluate the diagnostic performance of the SleepImage Ring device in identifying obstructive sleep apnea (OSA) across different severity in comparison to standard polysomnography (PSG). Methods Thirty-nine patients (mean age, 56.8 ± 15.0 years; 29 [74.3%] males) were measured with the SleepImage Ring and PSG study simultaneously in order to evaluate the diagnostic performance of the SleepImage device for diagnosing OSA. Variables such as sensitivity, specificity, positive and negative likelihood ratio, positive and negative predictive value, and accuracy were calculated with PSG-AHI thresholds of 5, 15, and 30 events/h. Receiver operating characteristic curves were also built according to the above PSG-AHI thresholds. In addition, we analyzed the correlation and agreement between the apnea-hypopnea index (AHI) obtained from the two measurement devices. Results There was a strong correlation (r = 0.89, P < 0.001 and high agreement in AHI between the SleepImage Ring and standard PSG. Also, the SleepImage Ring showed reliable diagnostic capability, with areas under the receiver operating characteristic curve of 1.00 (95% CI, 0.91, 1.00), 0.90 (95% CI, 0.77, 0.97), and 0.98 (95% CI, 0.88, 1.000) for corresponding PSG-AHI of 5, 15 and 30 events/h, respectively. Conclusion The SleepImage Ring could be a clinically reliable and cheaper alternative to the gold standard PSG when aiming to diagnose OSA in adults.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-023-00304-9.

Mood Disorders are Correlated with Autonomic Nervous Function in Chronic Insomnia Patients with OSA

Purpose

To evaluate the correlation between sleep microstructure, autonomic nervous system activity, and neuropsychological characteristics in chronic insomnia (CI) patients with obstructive sleep apnea (OSA).

Patients and Methods

Forty-five CI-OSA patients, forty-six CI patients and twenty-two matched healthy control subjects (HCs) were enrolled. CI-OSA patients were then divided into two groups: mild OSA and moderate-to-severe OSA. All participants completed neuropsychological tests, which included the Hamilton Depression and Anxiety Scales (HAMD and HAMA), the Pittsburgh Sleep Quality Index (PSQI), the Insomnia Severity Index (ISI), the Epworth Sleepiness Scale (ESS), and the Mini-mental State Examination (MMSE). The autonomic nervous system activity and sleep microstructure were examined by the PSM-100A.

Results

The CI-OSA patients exhibited higher scores on the PSQI, ESS, ISI, HAMA, and HAMD than HCs and CI patients (all p < 0.01). The CI-OSA patients had a lower proportion of stable sleep, REM sleep and a higher proportion of unstable sleep ratio (all p < 0.01) than HCs and CI patients (all p < 0.01). The CI-OSA patients had higher ratios of LF and LF/HF, and lower ratios of HF and Pnn50% (all p < 0.01) than HCs and CI patients (all p < 0.01). Compared to CI-mild OSA patients, the CI-moderate-to-severe OSA patients presented with a higher ESS scores, higher ratios of LF and LF/HF, and lower ratios of HF (all p < 0.05). In CI-OSA patients, higher HAMD scores were correlated with decreased MMSE scores (r=-0.678, p < 0.01). A higher LF ratio was correlated with higher HAMD and HAMA scores (r=0.321, p=0.031, r =0.449, p =0.002), and a higher HF ratio was correlated with lower HAMD and HAMA scores (r=-0.321, P =0.031, r =-0.449, p =0.002).

Conclusion

OSA exacerbates the abnormalities of sleep microstructure and the autonomic nervous dysfunction in CI patients. Dysfunction of the autonomic nervous system could contribute to mood deterioration in CI with OSA patients.

A novel deep domain adaptation method for automated detection of sleep apnea/hypopnea events

Objective.Sleep apnea-hypopnea syndrome (SAHS) is a common sleep-related respiratory disorder that is generally assessed for severity using polysomnography (PSG); however, the diversity of sampling devices and patients makes this not only costly but may also degrade the performance of the algorithms.Approach.This paper proposes a novel deep domain adaptation module which uses a long short-term memory-convolutional neural network embedded with the channel attention mechanism to achieve autonomous extraction of high-quality features. Meanwhile, a domain adaptation module was built to achieve domain-invariant feature extraction for reducing the differences in data distribution caused by different devices and other factors. In addition, during the training process, the algorithm used the last second label as the label of the PSG segment, so that second-by-second evaluation of respiratory events could be achieved.Main results.The algorithm applied the two datasets provided by PhysioNet as the source and target domains. The accuracy, sensitivity and specificity of the algorithm on the source domain were 86.46%, 86.11% and 93.17%, respectively, and on the target domain were 83.63%, 82.52%, 91.62%, respectively. The proposed algorithm showed strong generalization ability and the classification results were comparable to the current advanced methods. Besides, the apnea-hypopnea index values estimated by the proposed algorithm showed a high correlation with the manual scoring values on both domains.Significance.The proposed algorithm can effectively perform SAHS detection and evaluation with certain generalization.

A Novel Approach for Sleep Arousal Disorder Detection Based on the Interaction of Physiological Signals and Metaheuristic Learning

The vast majority of sleep disturbances are caused by various types of sleep arousal. To diagnose sleep disorders and prevent health problems such as cardiovascular disease and cognitive impairment, sleep arousals must be accurately detected. Consequently, sleep specialists must spend considerable time and effort analyzing polysomnography (PSG) recordings to determine the level of arousal during sleep. The development of an automated sleep arousal detection system based on PSG would considerably benefit clinicians. We quantify the EEG-ECG by using Lyapunov exponents, fractals, and wavelet transforms to identify sleep stages and arousal disorders. In this paper, an efficient hybrid-learning method is introduced for the first time to detect and assess arousal incidents. Modified drone squadron optimization (mDSO) algorithm is used to optimize the support vector machine (SVM) with radial basis function (RBF) kernel. EEG-ECG signals are preprocessed samples from the SHHS sleep dataset and the PhysioBank challenge 2018. In comparison to other traditional methods for identifying sleep disorders, our physiological signals correlation innovation is much better than similar approaches. Based on the proposed model, the average error rate was less than 2%-7%, respectively, for two-class and four-class issues. Additionally, the proper classification of the five sleep stages is determined to be accurate 92.3% of the time. In clinical trials of sleep disorders, the hybrid-learning model technique based on EEG-ECG signal correlation features is effective in detecting arousals.

ECG Patient Simulator Based on Mathematical Models

In this work, we propose a versatile, low-cost, and tunable electronic device to generate realistic electrocardiogram (ECG) waveforms, capable of simulating ECG of patients within a wide range of possibilities. A visual analysis of the clinical ECG register provides the cardiologist with vital physiological information to determine the patient's heart condition. Because of its clinical significance, there is a strong interest in algorithms and medical ECG measuring devices that acquire, preserve, and process ECG recordings with high fidelity. Bearing this in mind, the proposed electronic device is based on four different mathematical models describing macroscopic heartbeat dynamics with ordinary differential equations. Firstly, we produce full 12-lead ECG profiles by implementing a model comprising a network of heterogeneous oscillators. Then, we implement a discretized reaction-diffusion model in our electronic device to reproduce ECG waveforms from various rhythm disorders. Finally, in order to show the versatility and capabilities of our system, we include two additional models, a ring of three coupled oscillators and a model based on a quasiperiodic motion, which can reproduce a wide range of pathological conditions. With this, the proposed device can reproduce around thirty-two cardiac rhythms with the possibility of exploring different parameter values to simulate new arrhythmias with the same hardware. Our system, which is a hybrid analog-digital circuit, generates realistic ECG signals through digital-to-analog converters whose amplitudes and waveforms are controlled through an interactive and friendly graphic interface. Our ECG patient simulator arises as a promising platform for assessing the performance of electrocardiograph equipment and ECG signal processing software in clinical trials. Additionally the produced 12-lead profiles can be tested in patient monitoring systems.

Associations of Reduced Sympathetic Neural Activity and Elevated Baroreflex Sensitivity With Non-Rapid Eye Movement Sleep: Evidence From Electroencephalogram- and Electrocardiogram-Based Sleep Staging

OBJECTIVE

Autonomic neural controls in sleep regulation have been previously demonstrated; however, whether these alternations can be observed by different sleep staging approaches remains unclear. Two established methods for sleep staging-the standardized visual scoring and the cardiopulmonary coupling (CPC) analysis based on electrocardiogram-were used to explore the cardiovascular profiles of sleep.

METHODS

Overnight polysomnography was recorded together with continuous beat-to-beat blood pressure. Cortical activity, heart rate variability, blood pressure variability, and baroreflex sensitivity during sleep stages from 24 nights of sleep were obtained from 15 normotensive participants and analyzed.

RESULTS

Non-rapid eye movement sleep (NREM) from visual scoring and restful sleep (RS) of CPC both showed the highest delta power of electroencephalogram (EEG) and lowest beta activity of EEG in comparison with other sleep stages (p < .001); likewise, the lowest total power of heart rate variability and suppressed vascular-sympathetic activity, reflected by low-frequency power of blood pressure variability, as well as a trend in elevated baroreflex sensitivity, were observed in the NREM or RS. This suppressed vascular-sympathetic activity during stable sleep further exhibited a significant correlation with increased slow-wave activity (NREM: r = -0.292 ± 0.34, p = .002; RS: r = -0.209 ± 0.30, p = .010).

CONCLUSIONS

Autonomic nervous system is evidently associated with stable sleep, as indicated by the similar findings obtained from sleep stages categorized by standardized visual scoring or CPC analysis. Such association between cardiovascular neural activity and sleep EEGs can be observed regardless of the sleep staging approach followed.

Slow wave synchronization and sleep state transitions

Spontaneous synchronization over large networks is ubiquitous in nature, ranging from inanimate to biological systems. In the human brain, neuronal synchronization and de-synchronization occur during sleep, with the greatest degree of neuronal synchronization during slow wave sleep (SWS). The current sleep classification schema is based on electroencephalography and provides common criteria for clinicians and researchers to describe stages of non-rapid eye movement (NREM) sleep as well as rapid eye movement (REM) sleep. These sleep stage classifications have been based on convenient heuristic criteria, with little consideration of the accompanying normal physiological changes across those same sleep stages. To begin to resolve those inconsistencies, first focusing only on NREM sleep, we propose a simple cluster synchronization model to explain the emergence of SWS in healthy people without sleep disorders. We apply the empirical mode decomposition (EMD) analysis to quantify slow wave activity in electroencephalograms, and provide quantitative evidence to support our model. Based on this synchronization model, NREM sleep can be classified as SWS and non-SWS, such that NREM sleep can be considered as an intrinsically bistable process. Finally, we develop an automated algorithm for SWS classification. We show that this new approach can unify brain wave dynamics and their corresponding physiologic changes.

Cardiopulmonary Coupling

Cardiopulmonary coupling (CPC) is a technique that generates sleep spectrogram by calculating the cross-spectral power and coherence of heart rate variability and respiratory tidal volume fluctuations. There are several forms of CPC in the sleep spectrogram, which may provide information about normal sleep physiology and pathological sleep states. Since CPC can be calculated from any signal recording containing heart rate and respiration information, such as photoplethysmography (PPG) or blood pressure, it can be widely used in various applications, including wearables and non-contact devices. When derived from PPG, an automatic apnea-hypopnea index can be calculated from CPC-oximetry as PPG can be obtained from oximetry alone. CPC-based sleep profiling reveals the effects of stable and unstable sleep on sleep apnea, insomnia, cardiovascular regulation, and metabolic disorders. Here, we introduce, with examples, the current knowledge and understanding of the CPC technique, especially the physiological basis, analytical methods, and its clinical applications.

At-home wireless monitoring of acute hemodynamic disturbances to detect sleep apnea and sleep stages via a soft sternal patch

Obstructive sleep apnea (OSA) affects more than 900 million adults globally and can create serious health complications when untreated; however, 80% of cases remain undiagnosed. Critically, current diagnostic techniques are fundamentally limited by low throughputs and high failure rates. Here, we report a wireless, fully integrated, soft patch with skin-like mechanics optimized through analytical and computational studies to capture seismocardiograms, electrocardiograms, and photoplethysmograms from the sternum, allowing clinicians to investigate the cardiovascular response to OSA during home sleep tests. In preliminary trials with symptomatic and control subjects, the soft device demonstrated excellent ability to detect blood-oxygen saturation, respiratory effort, respiration rate, heart rate, cardiac pre-ejection period and ejection timing, aortic opening mechanics, heart rate variability, and sleep staging. Last, machine learning is used to autodetect apneas and hypopneas with 100% sensitivity and 95% precision in preliminary at-home trials with symptomatic patients, compared to data scored by professionally certified sleep clinicians.

Cardiopulmonary Sleep Spectrograms Open a Novel Window Into Sleep Biology-Implications for Health and Disease

The interactions of heart rate variability and respiratory rate and tidal volume fluctuations provide key information about normal and abnormal sleep. A set of metrics can be computed by analysis of coupling and coherence of these signals, cardiopulmonary coupling (CPC). There are several forms of CPC, which may provide information about normal sleep physiology, and pathological sleep states ranging from insomnia to sleep apnea and hypertension. As CPC may be computed from reduced or limited signals such as the electrocardiogram or photoplethysmogram (PPG) vs. full polysomnography, wide application including in wearable and non-contact devices is possible. When computed from PPG, which may be acquired from oximetry alone, an automated apnea hypopnea index derived from CPC-oximetry can be calculated. Sleep profiling using CPC demonstrates the impact of stable and unstable sleep on insomnia (exaggerated variability), hypertension (unstable sleep as risk factor), improved glucose handling (associated with stable sleep), drug effects (benzodiazepines increase sleep stability), sleep apnea phenotypes (obstructive vs. central sleep apnea), sleep fragmentations due to psychiatric disorders (increased unstable sleep in depression).

Evaluation of a non-contact ultra-wideband bio-radar sleep monitoring device for screening of sleep breathing disease

PURPOSE

Ultra-wideband bio-radar (UWB) is a new non-contact technology that can be used to screen for obstructive sleep apnea (OSA). However, little information is available regarding its reliability. This study aimed to evaluate the effectiveness of UWB and to determine if UWB could provide a novel and reliable method for the primary screening of sleep-related breathing disorders.

METHOD

Subjects with suspected OSA from the sleep center of the First Hospital of the China Medical University were assessed over the period of September 2018 to April 2019 for enrollment in the study. Three detection methods were simultaneously used, including the STOP-Bang questionnaire (SBQ), UWB, and standard polysomnography (PSG). The data were analyzed using a fourfold table, receiver operating characteristic curves, Spearman rank correlation coefficients, Bland-Altman plots, and epoch-by-epoch analysis.

RESULT

Of 67 patients, 56 were men, mean age was 43 ± 11 years, mean body mass index was 27.8 ± 4.8 kg/m², and mean SBQ score was 4.8 ± 1.6. The apnea-hypopnea index (AHI) (r = 0.82, p < 0.01) and minimum arterial oxygen saturation (r = 0.80, p < 0.01) of the UWB were positively correlated with those obtained from the PSG. UWB performed better than SBQ, as indicated by the larger area under the curve (0.85 vs. 0.632). The sensitivity and specificity of the UWB-AHI were good (100%, 70%, respectively).

CONCLUSIONS

UWB performs well in the screening of OSA and can provide reliable outcomes for the screening of OSA at the primary level.

Enhancing Obstructive Apnea Disease Detection Using Dual-Tree Complex Wavelet Transform-Based Features and the Hybrid "K-Means, Recursive Least-Squares" Learning for the Radial Basis Function Network

Background:

The obstructive sleep apnea (OSA) detection has become a hot research topic because of the high risk of this disease. In this paper, we tested some powerful and low computational signal processing techniques for this task and compared their results with the recent achievements in OSA detection.

Methods:

The Dual-tree complex wavelet transform (DT-CWT) is used in this paper to extract feature coefficients. From these coefficients, eight non-linear features are extracted and then reduced by the Multi-cluster feature selection (MCFS) algorithm. The remaining features are applied to the hybrid “K-means, RLS” RBF network which is a low computational rival for the Support vector machine (SVM) networks family.

Results and Conclusion:

The results showed suitable OSA detection percentage near 96% with a reduced complexity of nearly one third of the previously presented SVM based methods.

Impact of Sleep-Disordered Breathing on Functional Outcomes in Ischemic Stroke: A Cardiopulmonary Coupling Analysis

BACKGROUND AND PURPOSE

Cardiopulmonary coupling (CPC) analysis is an easily assessable method to evaluate sleep-disordered breathing (SDB); however, its prognostic impact in patients with acute ischemic stroke needs to be investigated. We performed a CPC analysis using Holter monitoring at the early stage of noncardioembolic ischemic stroke to investigate the prognostic effect of SDB on functional impairment at the 3-month follow-up.

METHODS

A total 615 patients with acute noncardioembolic ischemic stroke who underwent Holter monitoring within 30 days of stroke onset were enrolled from a multicenter, prospective, all-comer cohort. CPC analysis was conducted, and SDB was defined by the presence of narrow-band coupling during sleep time. We investigated the association between SDB and functional impairment at 3 months as measured by the modified Rankin Scale.

RESULT

Narrow-band coupling was present in 191 (31.1%) of 615 patients (mean age 64.5±12.6 years). The narrow-band group showed a significantly higher rate of severe functional impairment (modified Rankin Scale score >2; 45.5% versus 12.9%, P<0.001) and persistent disability (Δmodified Rankin Scale score ≤0; 53.9% versus 39.8%, P<0.001) at the 3-month follow-up. In multivariate analysis, narrow-band coupling was an independent predictor of higher risk of severe and persistent functional impairment at 3 months (odds ratio, 3.98 [95% CI, 2.34-6.78]; P<0.001; and odds ratio, 1.81 [95% CI, 1.23-2.66]; P<0.001, respectively). The results remained consistent after propensity-score matched analysis with 157 patient pairs (C-statistic=0.770).

CONCLUSIONS

SDB assessed by CPC analysis at the early stage of ischemic stroke could predict severe and prolonged functional impairment at 3 months. CPC analysis using Holter monitoring can help predicting functional impairment in acute ischemic stroke.

Introducing the Hybrid "K-means, RLS" Learning for the RBF Network in Obstructive Apnea Disease Detection using Dual-tree Complex Wavelet Transform Based Features

Apnea is one of the deadliest diseases that can be prevented and cured if it is detected in time. In this paper, we propose a precise method for early detection of the obstructive sleep apnea (OSA) disease using the latest feature selection and extraction methods. The feature selection in this paper is based on the Dual tree complex wavelet (DT-CWT) coefficients of the ECG signals of several patients. The feature extraction from these coefficients is done using frequency and time techniques. The Feature selection is done using the spectral regression discriminant analysis (SRDA) algorithm and the classification is performed using the hybrid RBF network. A hybrid RBF neural network is introduced in this paper for detecting apnea that is much less computationally demanding than the previously presented SVM networks. Our findings showed a 3 percent improvement in the detection and at least a 30 percent reduction in the computational complexity in comparison with methods that have been presented recently.